Triple

T5912198
Position Surface form Disambiguated ID Type / Status
Subject Antananarivo E131488 entity
Predicate hasLandmark P105 FINISHED
Object Rova of Antananarivo
The Rova of Antananarivo is a historic royal palace complex that served as the political and spiritual center of the Merina monarchy in Madagascar.
E556864 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Rova of Antananarivo | Statement: [Antananarivo, hasLandmark, Rova of Antananarivo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rova of Antananarivo
Context triple: [Antananarivo, hasLandmark, Rova of Antananarivo]
  • A. Maromokotro
    Maromokotro is the tallest mountain in Madagascar, located in the island’s northern highlands.
  • B. Anjara
    Anjara is a town in northern Jordan situated within the hilly, forested region of Ajloun, known for its Christian pilgrimage sites and scenic landscapes.
  • C. Mahafaly Malagasy
    Mahafaly Malagasy is a regional variety of the Malagasy language spoken primarily by the Mahafaly people in southwestern Madagascar.
  • D. Antsirabe
    Antsirabe is a highland city in central Madagascar known for its cool climate, thermal springs, and colonial-era architecture.
  • E. Rahaita
    Rahaita is a settlement located in Eritrea's Southern Red Sea Region, along the country's arid Red Sea coastal area.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Rova of Antananarivo
Triple: [Antananarivo, hasLandmark, Rova of Antananarivo]
Generated description
The Rova of Antananarivo is a historic royal palace complex that served as the political and spiritual center of the Merina monarchy in Madagascar.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Rova of Antananarivo
Target entity description: The Rova of Antananarivo is a historic royal palace complex that served as the political and spiritual center of the Merina monarchy in Madagascar.
  • A. Maromokotro
    Maromokotro is the tallest mountain in Madagascar, located in the island’s northern highlands.
  • B. Anjara
    Anjara is a town in northern Jordan situated within the hilly, forested region of Ajloun, known for its Christian pilgrimage sites and scenic landscapes.
  • C. Mahafaly Malagasy
    Mahafaly Malagasy is a regional variety of the Malagasy language spoken primarily by the Mahafaly people in southwestern Madagascar.
  • D. Antsirabe
    Antsirabe is a highland city in central Madagascar known for its cool climate, thermal springs, and colonial-era architecture.
  • E. Rahaita
    Rahaita is a settlement located in Eritrea's Southern Red Sea Region, along the country's arid Red Sea coastal area.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69c008593a44819081a07ae0efe6c574 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c037b6f48c8190b60a32e5f64fe254 completed March 22, 2026, 6:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0c015b90081909777ac5ed80e927c completed March 23, 2026, 4:22 a.m.
NEDg Description generation batch_69c0c1bf78908190933360b1099b1444 completed March 23, 2026, 4:29 a.m.
NED2 Entity disambiguation (via description) batch_69c0c240c3ac8190895c621c3d326bfd completed March 23, 2026, 4:32 a.m.
Created at: March 22, 2026, 3:59 p.m.